Triple
T37241699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Efe people |
E923727
|
entity |
| Predicate | exchangePractice |
P9798
|
FINISHED |
| Object | trade forest products for cultivated foods |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: trade forest products for cultivated foods | Statement: [Efe people, exchangePractice, trade forest products for cultivated foods]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exchangePractice Context triple: [Efe people, exchangePractice, trade forest products for cultivated foods]
-
A.
exchangeAuthority
Indicates a relationship where control or decision-making power is transferred or swapped between entities.
-
B.
exchangeType
Indicates the kind or category of exchange occurring between entities, such as the method, direction, or nature of what is being traded or transferred.
-
C.
exchangeRegime
Indicates the type of currency exchange system or policy framework governing how a country’s currency is valued and traded relative to other currencies.
-
D.
exchange
chosen
Indicates a reciprocal transfer of something (such as goods, information, or services) between two or more entities.
-
E.
exchangeMIC
Indicates a relationship where two entities mutually trade or swap MIC (e.g., a specific resource, code, or identifier) with each other.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76ea9fee88190a589f661d95a7189 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.